About the othinus tag
othinus is a character tag that NovelAI Diffusion can use. On Danbooru it has 321 posts, and its best-rated still image scores 198. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws othinus
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing othinus in a prompt
Put the subject first, then this tag, then quality tags.
othinus, solo, best quality, masterpiecewlop, othinus, soloThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
A Magic God that was based on Norse mythology Odin. Magic God are the purest, most perfect Magician that encompasses every possibility, including positive and negative (thus all her magic always has 50/50 chance of succeeding). She wield Gungnir to cover her 50/50 weakness, and to remake the world.
At the end of her arc, she uses "Turn to Fairy" spell to undo her status as a Magic God and killing her. But due to Kamijou Touma's Imagine Breaker interrupting the magic, she survived the spell and turned into 15cm fairy who lost all of her magic.
FAQ
Does NovelAI recognize othinus?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from othinus.
How do I write othinus in a prompt?
Write "othinus" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.
